What it is
A Node.js profanity and toxicity screener for real-time chat and game moderation. It detects leetspeak, character spacing, romanized and code-mixed profanity across English and Indic languages including Kannada, Telugu, Tamil, Hindi, and Bengali.
How it uses Jev
Jev acts as a reflex-speed System One classifier. Given the input text as state, it answers typed questions about profanity, toxicity, severity, language, obfuscation type, and action. The returned calibrated probabilities are mapped to booleans, severity scores, and moderation actions in code.
Primitives:choicescore
Technique worth stealing
Route ambiguous or context-dependent cases to human review instead of forcing a binary decision.
Try it
npm install gg-friggin-ez, set OPENROUTER_API_KEY, then call isProfane() or screen().
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.79
- Shows a System One patternno0.09
- Handles uncertaintyno0.05
- Measuredyes0.61
- Runnableyes0.97
- Worth recommendingno0.21
- Model replicano0.12
- Problem scopescore on a 0–2 scale1.93
- About Jevyes0.78
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.